We maintain strong expertise in text mining and cognitive sciences (e.g. natural language processing & computational linguistics, logics and ontology engineering, webometrics...). Our group gathers expertise to optimally process clinical files (e.g. Electronic Health Records, Clinical Trials...), literature, and intellectual property contents (patents, consent forms...). We are familiar with processing multilingual contents (English, French, Chinese...), health and pharmaceutical industry standards (HL7, CDISC...), knowledge management (Collaborative environments, Ontology editors...), as well as Web/Social media.
Today, our main applications include instruments to support the functional curation of gene products, search and question-answering engines to navigate literature and patent collection, and decision-support systems for clinicians and pharmaceutical companies.


In the context of this large European Research Infrastructure project, we aim to increase cross-references between curated SIB databases and Europe PMC.

WeIRD (Web Intelligence for Rare Disease)

The WeIRD project aims to provide the informational instruments needed to navigate, search and ultimately question the web evidence space of Rare Diseases by providing access to high-quality specific content that can be helpful in diagnosing Rare Diseases. The system will use advanced information retrieval and text mining methods to holistically crawl, index and finally analyse all the explicit and implicit knowledge available on Rare Diseases.


The EXPAND project aims to exploit a number of selected eHealth assets developed in various initiatives in order to move from a set of point-solution pilots to a large-scale deployment of cross-border facilities. All of this with the aim of supporting Member States (MS) in delivering their local eHealth plans and improving cross-border care.


Thanks to the support of the SNF, the CALIPHO Group and our group are joining forces to develop the next generation literature-based biocuration platform for proteomics. The CALIPHO group maintains the neXtProt molecular biology database.


MD-Paedigree represents a clinically-driven and strongly VPH-rooted project. Seven world-renowned clinical centres of excellence pursue improved interoperability of paediatric biomedical information, data and knowledge by developing together a set of reusable and adaptable multi-scale models for more predictive, individualized, effective and safer paediatric healthcare.


ChemQuest gathers various Novartis-supported studies and managed services, including an original patent search engine, a multilingual curation pipeline for oncology and clinical trial reports, as well as a competitive intelligence platform for the web.

RESIPI and Knomie

The aim of these CTI supported projects is the development of an automatic web alerting system to monitor the life-cycle of emerging knowledge-intensive technologies.

KHRESMOI: Knowledge Helper for Medical and Other Information users

A multi-modal search and access system for biomedical information and documents to federate literature (MEDLINE), including full-text contents (e.g. PubMed Central), knowledge bases (e.g. Orphanet, OMIM...), and web contents (e.g. Wikipedia, Cochrane,...).

More information about our research